Predicting User Roles in Social Networks using Transfer Learning with Feature Transformation

TL;DR

This paper introduces a transfer learning method that uses feature transformation to classify social roles in unlabelled social networks, demonstrated through experiments on real-world data.

Contribution

It proposes a novel transfer learning approach leveraging feature transformation for social role classification in unlabelled networks.

Findings

Effective role prediction on real-world datasets

Outperforms baseline methods in accuracy

Generalizes well across different social networks

Abstract

How can we recognise social roles of people, given a completely unlabelled social network? We present a transfer learning approach to network role classification based on feature transformations from each network's local feature distribution to a global feature space. Experiments are carried out on real-world datasets. (See manuscript for the full abstract.)